Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions .gitignore
Original file line number Diff line number Diff line change
Expand Up @@ -36,3 +36,4 @@ packages/example/build
packages/example-without-zod/build
packages/docs/out
packages/cloudrun/container/ensure-browser.mjs
packages/skills-evals/.runs
19 changes: 19 additions & 0 deletions bun.lock

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

1 change: 1 addition & 0 deletions package.json
Original file line number Diff line number Diff line change
Expand Up @@ -85,6 +85,7 @@
"!packages/template-audiogram/whisper.cpp",
"!packages/template-audiogram/whisper.cpp/**",
"!packages/template-vercel/**",
"!packages/skills-evals/.runs/**",
"!packages/bugs"
],
"catalog": {
Expand Down
1 change: 1 addition & 0 deletions packages/cli/src/list-of-remotion-packages.ts
Original file line number Diff line number Diff line change
Expand Up @@ -65,6 +65,7 @@ export const listOfRemotionPackages = [
'@remotion/serverless',
'@remotion/serverless-client',
'@remotion/skills',
'@remotion/skills-evals',
'@remotion/studio-server',
'@remotion/studio-shared',
'@remotion/studio',
Expand Down
1 change: 1 addition & 0 deletions packages/create-video/src/list-of-remotion-packages.ts
Original file line number Diff line number Diff line change
Expand Up @@ -65,6 +65,7 @@ export const listOfRemotionPackages = [
'@remotion/serverless',
'@remotion/serverless-client',
'@remotion/skills',
'@remotion/skills-evals',
'@remotion/studio-server',
'@remotion/studio-shared',
'@remotion/studio',
Expand Down
5 changes: 5 additions & 0 deletions packages/skills-evals/README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
# @remotion/skills-evals

## Usage

This is an internal package and has no documentation.
7 changes: 7 additions & 0 deletions packages/skills-evals/eslint.config.mjs
Original file line number Diff line number Diff line change
@@ -0,0 +1,7 @@
import {remotionFlatConfig} from '@remotion/eslint-config-internal';

const config = remotionFlatConfig({react: false});

export default {
...config,
};
29 changes: 29 additions & 0 deletions packages/skills-evals/package.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,29 @@
{
"repository": {
"url": "https://github.com/remotion-dev/remotion/tree/main/packages/skills-evals"
},
"name": "@remotion/skills-evals",
"version": "4.0.461",
"private": true,
"type": "module",
"scripts": {
"dev": "bun src/server.tsx",
"eval": "bun src/cli.ts",
"format": "oxfmt src scenarios.ts",
"formatting": "oxfmt src scenarios.ts --check",
"lint": "eslint src && tsgo"
},
"dependencies": {
"@remotion/skills": "workspace:*",
"react": "catalog:",
"react-dom": "catalog:"
},
"devDependencies": {
"@remotion/eslint-config-internal": "workspace:*",
"@types/bun": "catalog:",
"@types/react": "catalog:",
"@types/react-dom": "catalog:",
"@typescript/native-preview": "catalog:",
"eslint": "catalog:"
}
}
8 changes: 8 additions & 0 deletions packages/skills-evals/scenarios.ts
Original file line number Diff line number Diff line change
@@ -0,0 +1,8 @@
export type SkillEvalScenario = {
id: string;
model: string;
prompt: string;
timeoutMs?: number;
};

export const scenarios: SkillEvalScenario[] = [];
67 changes: 67 additions & 0 deletions packages/skills-evals/src/app/comparison-data.ts
Original file line number Diff line number Diff line change
@@ -0,0 +1,67 @@
import {existsSync} from 'node:fs';
import {readFile} from 'node:fs/promises';
import {join} from 'node:path';
import {listFilesRecursively, readJson, sanitizePathPart} from '../files';
import type {SkillEvalComparison, SkillEvalManifest} from '../manifest';
import {comparisonsRoot} from './shared';

export type ComparisonWithManifests = {
afterManifest: SkillEvalManifest;
beforeManifest: SkillEvalManifest;
comparison: SkillEvalComparison;
skillDiff: string;
};

export const loadComparisons = async () => {
const files = (await listFilesRecursively(comparisonsRoot)).filter((file) =>
file.endsWith('/comparison.json'),
);
const comparisons = await Promise.all(
files.map((file) => readJson<SkillEvalComparison>(file)),
);

comparisons.sort((a, b) => b.completedAt.localeCompare(a.completedAt));

return comparisons;
};

export const getLatestComparisonByScenario = async () => {
const latest = new Map<string, SkillEvalComparison>();

for (const comparison of await loadComparisons()) {
if (!latest.has(comparison.scenarioId)) {
latest.set(comparison.scenarioId, comparison);
}
}

return latest;
};

export const loadComparison = async (
scenarioId: string,
comparisonId: string,
): Promise<ComparisonWithManifests | null> => {
const comparisonPath = join(
comparisonsRoot,
sanitizePathPart(scenarioId),
comparisonId,
'comparison.json',
);

if (!existsSync(comparisonPath)) {
return null;
}

const comparison = await readJson<SkillEvalComparison>(comparisonPath);
const [beforeManifest, afterManifest, skillDiff] = await Promise.all([
readJson<SkillEvalManifest>(comparison.before.manifestPath),
readJson<SkillEvalManifest>(comparison.after.manifestPath),
readFile(comparison.skillDiffPath, 'utf-8'),
]);

return {afterManifest, beforeManifest, comparison, skillDiff};
};

export const getPreferredArtifact = (manifest: SkillEvalManifest) =>
manifest.artifacts.find((artifact) => artifact.type === 'video') ??
manifest.artifacts[0];
Loading
Loading